CN111243743A - Data processing method, device, equipment and computer readable storage medium - Google Patents
Data processing method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111243743A CN111243743A CN202010057407.3A CN202010057407A CN111243743A CN 111243743 A CN111243743 A CN 111243743A CN 202010057407 A CN202010057407 A CN 202010057407A CN 111243743 A CN111243743 A CN 111243743A
- Authority
- CN
- China
- Prior art keywords
- person
- data processing
- data
- monitoring data
- processing method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Optimization (AREA)
- Biomedical Technology (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Pathology (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a data processing method, which comprises the following steps: regularly acquiring monitoring data of multiple dimensions corresponding to each person at intervals of a first preset time length; respectively carrying out normalization processing on the monitoring data of each dimension corresponding to each person; determining the similarity between every two persons, and determining a similarity matrix corresponding to each person based on the similarity; determining outliers among the individuals based on the similarity matrix. The invention also discloses a data processing device, equipment and a computer readable storage medium. The method and the system can monitor abnormal personnel in real time, and can conveniently and continuously track the state of the personnel in real time by excavating the abnormal points which may exist in the mass data, so that the potential reasons of the abnormal personnel are conveniently analyzed and excavated, and the abnormal events of the personnel in the sports event scene are reduced.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a data processing method, apparatus, device, and computer readable storage medium.
Background
In the sport scenario of a sports event, some athletes' injuries such as falls, sudden death, sudden cardiac arrest, physical discomfort, etc. are inevitably encountered due to weather or road reasons, etc.
At present, most of the abnormal events of athletes are followed by collecting physiological indexes and motion data of athletes and then making a preliminary judgment. These methods are basically performed by using conventional medical equipment, and cannot analyze and extract the potential cause of abnormality of the athlete in real time, so that the abnormal events of the athlete in the motion scene of the sports event are not reduced.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a data processing method, a data processing device, data processing equipment and a computer readable storage medium, and aims to solve the technical problem that at present, people with abnormalities in athletes are difficult to detect.
In order to achieve the above object, the present invention provides a data processing method, including the steps of:
regularly acquiring monitoring data of multiple dimensions corresponding to each person at intervals of a first preset time length;
respectively carrying out normalization processing on the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data;
determining the similarity between every two persons based on the normalized monitoring data of each dimension in each person, and determining a similarity matrix corresponding to each person based on the similarity;
determining outliers among the individuals based on the similarity matrix.
Further, the step of determining the similarity between each two persons based on the normalized monitoring data of each dimension in each person includes:
acquiring a mean value corresponding to the normalized monitoring data of each dimension in each person to obtain the mean value of each dimension corresponding to each person;
and determining the similarity between every two persons based on the mean value of each dimensionality corresponding to each person.
Further, the step of determining outlier persons among the persons based on the similarity matrix comprises:
performing dimension reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;
determining outliers among the individuals based on the two-dimensional matrix.
Further, the step of determining outliers of the individuals based on the two-dimensional matrix comprises:
processing the two-dimensional matrix based on an outlier detection algorithm to obtain local outlier factors corresponding to all the people;
determining outliers among the individuals based on the local outlier factor.
Further, after the step of determining outlier persons among the persons based on the similarity matrix, the data processing method further includes:
and displaying the state graphs of all the persons in a two-dimensional plane graph based on the local outlier factors, wherein the areas of the state graphs correspond to the local outlier factors one by one, and the colors of the state graphs of the persons except for the outliers are different from the colors of the state graphs of the outliers.
Further, after the step of displaying the status graph of each person in the two-dimensional plane graph based on the local outlier factor, the data processing method further includes:
when a first display instruction triggered based on a target state graph in each state graph is detected, acquiring target monitoring data of each dimensionality corresponding to the target state graph within a first preset time length;
and displaying a monitoring data curve of each dimension in the two-dimensional plane graph based on the target monitoring data of each dimension and the time sequence of each target monitoring data.
Further, after the step of displaying the status graph of each person in the two-dimensional plane graph based on the local outlier factor, the data processing method further includes:
updating the abnormal times corresponding to each person based on the outlier;
and displaying the identification information of the personnel with the current abnormity and the corresponding abnormity times in a first preset area of the two-dimensional plane map.
Further, after the step of normalizing the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data, the data processing method further includes:
splitting the normalized monitoring data based on a second preset time length to obtain multiple groups of sub-monitoring data corresponding to each person, wherein the first preset time length is an integral multiple of the second preset time length, and the sub-monitoring data comprise data of multiple dimensions;
adding the data of each dimension in the sub-monitoring data corresponding to each person respectively to obtain a comprehensive score corresponding to each person;
and respectively displaying the comprehensive scores corresponding to the personnel through the line graphs in a second preset area of the two-dimensional plane graph according to the time sequence of the comprehensive scores.
Further, after the step of displaying the comprehensive scores corresponding to the respective persons through line graphs in a second preset area of the two-dimensional plane graph according to the time sequence of the comprehensive scores, the data processing method further includes:
displaying a plurality of box whisker graphs in the second preset area based on a third preset time length, wherein the third preset time length is integral multiple of the second preset time length, and the first preset time length is integral multiple of the third preset time length;
when a second display instruction triggered by a target box whisker diagram in a plurality of box whisker diagrams is detected, acquiring the maximum score, the minimum score and the score mean value of the comprehensive scores of all personnel before the moment corresponding to the target box whisker diagram;
and displaying the obtained maximum score, the minimum score and the score mean value.
Further, after the step of displaying the comprehensive scores corresponding to the respective persons through line graphs in a second preset area of the two-dimensional plane graph according to the time sequence of the comprehensive scores, the data processing method further includes:
determining whether target normalized data with normalized data of each dimension in corresponding preset ranges exists in the normalized monitoring data corresponding to each person;
if the target normalized data exists, acquiring the acquisition time corresponding to the target normalized data and target personnel;
and displaying a preset graph in a line graph corresponding to the target person based on the acquisition time.
Further, to achieve the above object, the present invention also provides a data processing apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for regularly acquiring monitoring data of multiple dimensions corresponding to each person at intervals of a first preset time length;
the second acquisition module is used for respectively carrying out normalization processing on the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data;
the first determining module is used for determining the similarity between every two persons based on the normalized monitoring data of each dimension in each person and determining a similarity matrix corresponding to each person based on the similarity;
and the second determining module is used for determining outlier personnel in the personnel based on the similarity matrix.
Further, to achieve the above object, the present invention also provides a data processing apparatus comprising: a memory, a processor and a data processing program stored on the memory and executable on the processor, the data processing program, when executed by the processor, implementing the steps of the data processing method as described above.
Further, to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a data processing program which, when executed by a processor, implements the steps of the aforementioned data processing method.
The invention acquires the monitoring data of multiple dimensionalities corresponding to each person at intervals of a first preset time length, then, normalization processing is respectively carried out on the monitoring data of each dimension corresponding to each person to obtain the normalized monitoring data, then based on the normalized monitoring data of each dimension in each person, determining the similarity between each two persons, determining a similarity matrix corresponding to each person based on the similarity, finally determining outliers in each person based on the similarity matrix, monitoring abnormal persons in the persons in real time, by mining possible abnormal points (outlier personnel) from the mass data, medical personnel can know and continuously track the state of the personnel in real time, so as to analyze and mine the potential causes of the abnormal events of the personnel, and reduce the occurrence of the abnormal events of the personnel in the sports scene of the sports event.
Drawings
FIG. 1 is a block diagram of a data processing device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a data processing method according to a first embodiment of the present invention;
FIG. 3 is a schematic view of a display scenario in an embodiment of a data processing method according to the invention;
FIG. 4 is a schematic diagram of a display scenario in another embodiment of a data processing method according to the present invention;
FIG. 5 is a schematic diagram of a display scenario in another embodiment of the data processing method of the present invention;
FIG. 6 is a functional block diagram of a data processing apparatus according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a data processing device in a hardware operating environment according to an embodiment of the present invention.
The data processing device in the embodiment of the present invention may be a PC, or may be a mobile terminal device having a display function, such as a smart phone, a tablet computer, an electronic book reader, an MP3(Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3) player, an MP4(Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 4) player, a portable computer, or the like.
As shown in fig. 1, the data processing apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the data processing device may further include a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like.
Those skilled in the art will appreciate that the data processing device architecture shown in FIG. 1 does not constitute a limitation of the data processing device and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a data processing program.
In the data processing apparatus shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and communicating with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be used to invoke a data processing program stored in the memory 1005.
In this embodiment, the data processing apparatus includes: a memory 1005, a processor 1001 and a data processing program stored in the memory 1005 and operable on the processor 1001, wherein the processor 1001 calls the data processing program stored in the memory 1005 and executes the following operations in the data processing method.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the data processing method according to the present invention.
In this embodiment, the data processing method may be applied to a scene of a large-scale sports event, and may also be applied to scenes similar to other fields, for example, a marathon scene.
The data processing method comprises the following steps:
step S110, regularly acquiring monitoring data of multiple dimensions corresponding to each person at intervals of a first preset time length;
in this embodiment, each athlete (person) wears wearable devices such as a bracelet, and this wearable device can gather the data of a plurality of dimensions of the athlete, and upload the data of gathering to data processing device or data processing equipment in real time or regularly (interval is first to predetermine duration), and the monitoring data of a plurality of dimensions includes at least 3 in data such as the longitude and latitude information of the position that the athlete is currently located, present moment, current heart rate, current speed, current pace, current distance, current step frequency.
The monitoring data of multiple dimensions corresponding to each person refers to data of each dimension of each person within a first preset time period.
Step S120, normalization processing is respectively carried out on the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data;
in this embodiment, when the monitoring data of multiple dimensions corresponding to each person is obtained, normalization processing is performed on the monitoring data of each dimension of each person, so as to obtain normalized monitoring data, that is, normalized data of each dimension of each person is obtained, specifically, a min-max normalization algorithm may be used, and data of different dimensions are normalized to be within a (0, 1) range.
Step S130, determining the similarity between every two persons based on the normalized monitoring data of each dimension in each person, and determining a similarity matrix corresponding to each person based on the similarity;
in this embodiment, after the normalized monitoring data is obtained, according to the data normalized by each dimension of each person, the similarity between each two persons in each person, that is, the similarity between any two persons in each person, is determined, and according to the obtained similarity, a similarity matrix corresponding to each person is generated, where an element in the similarity matrix corresponding to each person is the similarity between the person and any other person.
And step S140, determining outliers in the people based on the similarity matrix.
In this embodiment, when the similarity matrix corresponding to each person is obtained, the outliers in each person are determined based on the similarity matrix, and specifically, the similarity matrix is processed by using an outlier detection algorithm to obtain an outlier matrix (outlier) corresponding to the similarity matrix, where the person corresponding to the outlier matrix is the outlier.
According to the technical scheme, abnormal points (outliers) which may exist can be automatically mined from mass data, medical staff can conveniently know and continuously track the states of the staff in real time, and information or signs which are ignored in monitoring data can be found out, and new knowledge experience is formed, so that similar events can be prevented from happening again in the following process.
The data processing method provided by this embodiment periodically obtains monitoring data of multiple dimensions corresponding to each person at intervals of a first preset duration, then performs normalization processing on the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data, then determines similarity between every two persons based on the normalized monitoring data of each dimension in each person, determines a similarity matrix corresponding to each person based on the similarity, and finally determines outliers in each person based on the similarity matrix, so as to monitor persons with abnormalities in real time, and excavate abnormal points (outliers) which may exist in mass data, thereby facilitating medical staff to know and continuously track states of persons in real time, and facilitating analysis and excavation of potential causes of abnormalities of persons, so as to reduce the occurrence of abnormal events of people in the sports scene of the sports event.
A second embodiment of the data processing method of the present invention is proposed based on the first embodiment, and in this embodiment, step S120 includes:
step S121, obtaining the mean value corresponding to the normalized monitoring data of each dimension in each person to obtain the mean value of each dimension corresponding to each person;
and S122, determining the similarity between every two persons based on the mean value of each dimensionality corresponding to each person.
In this embodiment, after obtaining the normalized monitoring data, according to the normalized data of each dimension of each person, a mean value corresponding to the normalized monitoring data of each dimension in each person is calculated, that is, the mean value of the normalized monitoring data of each dimension corresponding to each person is obtained, so as to obtain a brief data feature of each dimension corresponding to each person.
Then, based on the mean value of each dimension corresponding to each person, determining the similarity between each two persons in each person, specifically, calculating the similarity between each two persons in all dimensions by using a Canberra Distance formula, that is, the similarity between any two persons in each person, for example, generating a mean value vector based on the mean value of each dimension corresponding to each person according to a preset sequence, and calculating the similarity between each two persons in all dimensions by using the Canberra Distance formula according to the mean value vector of each person.
In the data processing method provided by this embodiment, the mean value corresponding to each dimension corresponding to each person is obtained by obtaining the mean value corresponding to the normalized monitoring data of each dimension in each person; then, the similarity between every two persons is determined based on the mean value of each dimension corresponding to each person, the similarity between every two persons can be accurately obtained according to the mean value of each dimension corresponding to each person, the accuracy of a similarity matrix and the data processing efficiency are improved, and the accuracy of outlier detection is further improved.
Based on the first embodiment, a third embodiment of the data processing method of the present invention is proposed, in which step S140 includes:
step S141, performing dimension reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;
and step S142, determining outliers in the persons based on the two-dimensional matrix.
In this embodiment, because the number of people is large, the dimension of the similarity matrix is also large, and in order to facilitate processing, the similarity matrix is subjected to dimension reduction processing to obtain a two-dimensional matrix corresponding to each person, specifically, the similarity matrix may be subjected to dimension reduction processing by using a T-SNE algorithm, where the T-SNE algorithm is a machine learning method for dimension reduction, and is capable of identifying associated patterns, and the T-SNE algorithm has a main advantage of maintaining the capability of local structures, that is, points with close distances in a high-dimensional data space are projected to a low dimension and are still close.
In the data processing method provided by this embodiment, the similarity matrix is subjected to dimension reduction processing to obtain a two-dimensional matrix corresponding to each person; and then determining outliers in the personnel based on the two-dimensional matrix, and performing dimension reduction processing on the similarity matrix to improve the data processing efficiency and further improve the detection efficiency of the outliers.
A fourth embodiment of the data processing method of the present invention is proposed based on the third embodiment, and in this embodiment, step S142 includes:
step S1421, processing the two-dimensional matrix based on an outlier detection algorithm to obtain local outlier factors corresponding to each person;
in step S1422, outliers among the individuals are determined based on the local outlier factors.
In this embodiment, after the two-dimensional matrix corresponding to each person is obtained, each two-dimensional matrix is processed by using an outlier detection algorithm, so as to obtain a local outlier factor corresponding to each person. Specifically, each two-dimensional matrix may be processed using an LOF outlier detection algorithm, which is a density-based algorithm whose most core part is a characterization of the density of data points, and the average density of the locations of sample points around a sample point is greater than the density of the locations of the sample points. The greater the local outlier factor is, the less dense the location of the point is than the locations of its surrounding samples, and the more likely this point is an outlier. Therefore, the people corresponding to the local outlier factor larger than 1 in the local outlier factors corresponding to the respective people are outliers.
Further, in an embodiment, after the step S140, the data processing method further includes:
and S150, displaying the state graphs of all the persons in a two-dimensional plane graph based on the local outlier factors, wherein the areas of the state graphs correspond to the local outlier factors one by one, and the colors of the state graphs of the persons except for the outliers are different from the colors of the state graphs of the outliers.
In this embodiment, two dimensions of the two-dimensional matrix are taken as coordinate axes of the two-dimensional plane graph, and the state graph of each person is displayed in the two-dimensional plane graph according to the two-dimensional matrix of each person, and the area of the state graph corresponds to the local outlier factor one to one, for example, referring to fig. 3, the state graph is a dot, the larger the local outlier factor is, the larger the radius of the dot is, the black dot is the state graph of other persons (normal persons) except for the outlier among the persons, and the gray dot is the state graph of the outlier, but a more prominent color, for example, red color, may also be adopted as the color of the state graph of the outlier. Wherein ppi in fig. 3 is the current heart rate, pace is the current pace, distance is the current distance, and speed is the current speed.
In the data processing method provided by this embodiment, the two-dimensional matrix is processed based on an outlier detection algorithm to obtain local outlier factors corresponding to each person; then, outliers in the people are determined based on the local outlier factors, and the outliers can be accurately determined according to the local outlier factors, so that the accuracy of detecting the outliers is improved.
A fifth embodiment of the data processing method of the present invention is proposed based on the fourth embodiment, and in this embodiment, after step S150, the data processing method further includes:
step S160, when a first display instruction triggered based on a target state graph in each state graph is detected, acquiring target monitoring data of each dimensionality corresponding to the target state graph within a first preset time length;
step S170, displaying a monitoring data curve of each dimension in a two-dimensional plane graph based on the target monitoring data of each dimension and the time sequence of each target monitoring data.
In this embodiment, a first display instruction may be triggered by double-click, single-click, or by suspending a cursor in a state graph, when a first display instruction triggered based on a target state graph in the state graphs is detected, target monitoring data of each dimension corresponding to the target state graph within a first preset time period is acquired, and then, based on the target monitoring data of each dimension and a time sequence of each target monitoring data, a monitoring data curve of each dimension is displayed in a two-dimensional plane graph, so that medical staff can view monitoring data of outliers in real time. Referring to fig. 3, the graph near the status graph in fig. 3 is a monitoring data graph of a certain person.
In the data processing method provided by this embodiment, when a first display instruction triggered based on a target state graph in each state graph is detected, target monitoring data of each dimension corresponding to the target state graph within a first preset time period is acquired; and then, based on the target monitoring data of each dimension and the time sequence of the target monitoring data, displaying the monitoring data curve of each dimension in a two-dimensional plane graph so as to facilitate medical personnel to check the monitoring data of the outliers in real time.
A sixth embodiment of the data processing method of the present invention is proposed based on the fourth embodiment, and in this embodiment, after step S150, the data processing method further includes:
step S180, updating the abnormal times corresponding to each person based on the outlier;
and step S190, displaying the identification information of the person with the current abnormity and the corresponding abnormity frequency in a first preset area of the two-dimensional plane map.
In this embodiment, after determining the outliers each time, the abnormal times of each person are accumulated, that is, the times of each person detected as the outliers are counted, and in a first preset area of the two-dimensional plane diagram, the identification information of the person with the current abnormality and the abnormal times of the person with the abnormality are displayed, referring to fig. 4, the first preset area is set below the state diagram in fig. 4, the identification information of the person with the abnormality is displayed in the first preset area one by one, if an abnormality occurs repeatedly in multiple time periods, the corresponding abnormal times of a person is greater than 1, the abnormal times of the person can be identified by a number at the upper right corner of the identification information, and the number can be displayed in red.
According to the data processing method provided by the embodiment, the abnormal times corresponding to each person are updated based on the outlier; and then, displaying the identification information of the person with the current abnormality and the corresponding abnormality times in a first preset area of the two-dimensional plane map so as to facilitate medical personnel to continuously monitor and diagnose the person and reduce the probability of the person being injured.
On the basis of the above-described respective embodiments, a sixth embodiment of the data processing method of the present invention is proposed, in the present embodiment, after step S120, the data processing method further includes:
step S200, splitting the normalized monitoring data based on a second preset time length to obtain multiple groups of sub-monitoring data corresponding to each person, wherein the first preset time length is an integral multiple of the second preset time length, and the sub-monitoring data comprises data of multiple dimensions;
step S210, adding the data of each dimension in the sub-monitoring data corresponding to each person to obtain a comprehensive score corresponding to each person;
and step S220, displaying the comprehensive scores corresponding to the personnel through the line graphs respectively in a second preset area of the two-dimensional plane graph according to the time sequence of the comprehensive scores.
In this embodiment, when the normalized monitoring data is obtained, the normalized monitoring data is split according to a second preset duration to obtain multiple sets of sub-monitoring data corresponding to each person, where the sub-monitoring data includes data of multiple dimensions within the second preset duration, that is, the normalized monitoring data of each person is segmented to obtain multiple pieces of data with the same duration, that is, sub-monitoring data. The second preset duration may be reasonably set according to the first preset duration, for example, when the first preset duration is 2 minutes, the second preset duration may be set to 5S.
And adding the data of each dimension in the sub-monitoring data corresponding to each person to obtain a plurality of comprehensive scores corresponding to each person, and adding the data of each dimension in the sub-monitoring data to obtain one comprehensive score for each sub-monitoring data of each person, wherein the number of the comprehensive scores is the same as that of the sub-monitoring data of each person.
When the comprehensive scores corresponding to the respective people are obtained, the comprehensive scores corresponding to the respective people are displayed through line graphs in a second preset area of the two-dimensional plane graph according to a time sequence of the comprehensive scores, specifically, the comprehensive scores corresponding to the respective people are displayed in the second preset area according to the time sequence, and the comprehensive scores corresponding to the respective people are connected to form a line graph, referring to fig. 3 and 5, wherein an upper area of fig. 3 is the second preset area, and fig. 5 is the second preset area.
Further, in an embodiment, after step S220, the data processing method further includes:
step a, displaying a plurality of box whisker graphs in a second preset area based on a third preset time length, wherein the third preset time length is an integral multiple of the second preset time length, and the first preset time length is an integral multiple of the third preset time length;
step b, when a second display instruction triggered by a target box whisker diagram in the plurality of box whisker diagrams is detected, acquiring the maximum score, the minimum score and the score mean value of the comprehensive scores of all the personnel before the moment corresponding to the target box whisker diagram;
and c, displaying the obtained maximum score, the minimum score and the score mean value.
Wherein, the box whisker chart is a statistical chart used for displaying a group of data dispersion condition data. The shape of the box is called, and the maximum value, the minimum value, the median and the upper quartile and the lower quartile of a group of data can be displayed through the energy box and whisker diagram. The third preset time period may be set as appropriate, for example, the first preset time period is 2 minutes, the second preset time period is 5S, and the third preset time period is 20S.
In this embodiment, based on a third preset duration, a plurality of box whisker diagrams are displayed in the second preset area, specifically, referring to fig. 3 and 5, one box whisker diagram is drawn in the second preset area every 20 seconds, a medical staff may trigger a second display instruction through operations such as clicking, double-clicking, and the like, when the second display instruction is detected, a target box whisker diagram in the plurality of box whisker diagrams is determined according to the second display instruction, namely, triggering the box whisker chart of the second display instruction, and acquiring the maximum score, the minimum score and the score mean value of the comprehensive scores of all the personnel before the moment corresponding to the target box whisker chart, and then displaying the obtained maximum score, the minimum score and the score mean value so as to conveniently check the distribution conditions of the maximum score, the minimum score, the score mean value and the like of the comprehensive scores of all the personnel and perform transverse comparison of a plurality of time point data.
Further, in another embodiment, after step S220, the data processing method further includes:
d, determining whether target normalized data with the normalized data of each dimension in the normalized monitoring data corresponding to each person is in a corresponding preset range or not;
step e, if the target normalized data exists, acquiring the acquisition time corresponding to the target normalized data and the target personnel;
and f, displaying a preset graph in the line graph corresponding to the target person based on the acquisition time.
In this embodiment, a preset range of each dimension may be preset, data in the preset range is abnormal data, when normalized monitoring data corresponding to each person is obtained, it is determined whether target normalized data in which the normalized data of each dimension is in the corresponding preset range exists in the normalized monitoring data corresponding to each person, each dimension data in the target normalized data is in the preset range of the corresponding dimension, if yes, an acquisition time and a target person corresponding to the target normalized data are obtained, and a preset pattern is displayed in a line graph corresponding to the target person according to the acquisition time, for example, a dot is displayed in the line graph, so as to check the abnormal person data at a single time.
In the data processing method provided by this embodiment, the normalized monitoring data is split based on the second preset time length to obtain multiple groups of sub-monitoring data corresponding to each person, and then the data of each dimension in the sub-monitoring data corresponding to each person are added to obtain the comprehensive score corresponding to each person; and then in a second preset area of the two-dimensional plane graph, according to the time sequence of the comprehensive scores, the comprehensive scores corresponding to all the personnel are displayed through the line graphs respectively, so that the medical personnel can conveniently check the states of the personnel through the line graphs, the medical personnel can conveniently and continuously monitor and diagnose the personnel, and the probability of injury events of the personnel is reduced.
An embodiment of the present invention further provides a data processing apparatus, and referring to fig. 6, the data processing apparatus includes:
the first obtaining module 110 is configured to obtain monitoring data of multiple dimensions corresponding to each person at regular intervals of a first preset time length;
the second obtaining module 120 is configured to perform normalization processing on the monitoring data of each dimension corresponding to each person, so as to obtain normalized monitoring data;
a first determining module 130, configured to determine similarity between each two persons based on the normalized monitoring data of each dimension in each person, and determine a similarity matrix corresponding to each person based on the similarity;
a second determining module 140 for determining outlier persons among the persons based on the similarity matrix.
Further, the first determining module 130 is further configured to:
acquiring a mean value corresponding to the normalized monitoring data of each dimension in each person to obtain the mean value of each dimension corresponding to each person;
and determining the similarity between every two persons based on the mean value of each dimensionality corresponding to each person.
Further, the second determining module 140 is further configured to:
performing dimension reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;
determining outliers among the individuals based on the two-dimensional matrix.
Further, the second determining module 140 is further configured to:
processing the two-dimensional matrix based on an outlier detection algorithm to obtain local outlier factors corresponding to all the people;
determining outliers among the individuals based on the local outlier factor.
Further, the data processing apparatus further includes:
and displaying the state graphs of all the persons in a two-dimensional plane graph based on the local outlier factors, wherein the areas of the state graphs correspond to the local outlier factors one by one, and the colors of the state graphs of the persons except for the outliers are different from the colors of the state graphs of the outliers.
Further, the data processing apparatus further includes:
when a first display instruction triggered based on a target state graph in each state graph is detected, acquiring target monitoring data of each dimensionality corresponding to the target state graph within a first preset time length;
and displaying a monitoring data curve of each dimension in the two-dimensional plane graph based on the target monitoring data of each dimension and the time sequence of each target monitoring data.
Further, the data processing apparatus further includes:
updating the abnormal times corresponding to each person based on the outlier;
and displaying the identification information of the personnel with the current abnormity and the corresponding abnormity times in a first preset area of the two-dimensional plane map.
Further, the data processing apparatus further includes:
splitting the normalized monitoring data based on a second preset time length to obtain multiple groups of sub-monitoring data corresponding to each person, wherein the first preset time length is an integral multiple of the second preset time length, and the sub-monitoring data comprise data of multiple dimensions;
adding the data of each dimension in the sub-monitoring data corresponding to each person respectively to obtain a comprehensive score corresponding to each person;
and respectively displaying the comprehensive scores corresponding to the personnel through the line graphs in a second preset area of the two-dimensional plane graph according to the time sequence of the comprehensive scores.
Further, the data processing apparatus further includes:
displaying a plurality of box whisker graphs in the second preset area based on a third preset time length, wherein the third preset time length is integral multiple of the second preset time length, and the first preset time length is integral multiple of the third preset time length;
when a second display instruction triggered by a target box whisker diagram in a plurality of box whisker diagrams is detected, acquiring the maximum score, the minimum score and the score mean value of the comprehensive scores of all personnel before the moment corresponding to the target box whisker diagram;
and displaying the obtained maximum score, the minimum score and the score mean value.
Further, the data processing apparatus further includes:
determining whether target normalized data with normalized data of each dimension in corresponding preset ranges exists in the normalized monitoring data corresponding to each person;
if the target normalized data exists, acquiring the acquisition time corresponding to the target normalized data and target personnel;
and displaying a preset graph in a line graph corresponding to the target person based on the acquisition time.
The method executed by each program module can refer to each embodiment of the data processing method of the present invention, and is not described herein again.
In addition, the embodiment of the invention also provides a computer readable storage medium.
The computer readable storage medium has stored thereon a data processing program which, when executed by a processor, implements the steps of the data processing method as described above.
The method implemented when the data processing program running on the processor is executed may refer to each embodiment of the data processing method of the present invention, and details are not described here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (13)
1. A data processing method, characterized in that the data processing method comprises the steps of:
regularly acquiring monitoring data of multiple dimensions corresponding to each person at intervals of a first preset time length;
respectively carrying out normalization processing on the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data;
determining the similarity between every two persons based on the normalized monitoring data of each dimension in each person, and determining a similarity matrix corresponding to each person based on the similarity;
determining outliers among the individuals based on the similarity matrix.
2. The data processing method of claim 1, wherein the step of determining the similarity between each of the persons based on the normalized monitoring data for each of the dimensions of each of the persons comprises:
acquiring a mean value corresponding to the normalized monitoring data of each dimension in each person to obtain the mean value of each dimension corresponding to each person;
and determining the similarity between every two persons based on the mean value of each dimensionality corresponding to each person.
3. The data processing method of claim 1, wherein the step of determining outlier persons among the persons based on the similarity matrix comprises:
performing dimension reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;
determining outliers among the individuals based on the two-dimensional matrix.
4. A data processing method as claimed in claim 3, wherein the step of determining outlier persons among the persons based on the two-dimensional matrix comprises:
processing the two-dimensional matrix based on an outlier detection algorithm to obtain local outlier factors corresponding to all the people;
determining outliers among the individuals based on the local outlier factor.
5. The data processing method of claim 4, wherein after the step of determining outlier persons among the persons based on the similarity matrix, the data processing method further comprises:
and displaying the state graphs of all the persons in a two-dimensional plane graph based on the local outlier factors, wherein the areas of the state graphs correspond to the local outlier factors one by one, and the colors of the state graphs of the persons except for the outliers are different from the colors of the state graphs of the outliers.
6. The data processing method of claim 5, wherein after the step of presenting the status graphic of each person in a two-dimensional plan view based on the local outlier factor, the data processing method further comprises:
when a first display instruction triggered based on a target state graph in each state graph is detected, acquiring target monitoring data of each dimensionality corresponding to the target state graph within a first preset time length;
and displaying a monitoring data curve of each dimension in the two-dimensional plane graph based on the target monitoring data of each dimension and the time sequence of each target monitoring data.
7. The data processing method of claim 5, wherein after the step of presenting the status graphic of each person in a two-dimensional plan view based on the local outlier factor, the data processing method further comprises:
updating the abnormal times corresponding to each person based on the outlier;
and displaying the identification information of the personnel with the current abnormity and the corresponding abnormity times in a first preset area of the two-dimensional plane map.
8. The data processing method according to any one of claims 1 to 7, wherein after the step of normalizing the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data, the data processing method further comprises:
splitting the normalized monitoring data based on a second preset time length to obtain multiple groups of sub-monitoring data corresponding to each person, wherein the first preset time length is an integral multiple of the second preset time length, and the sub-monitoring data comprise data of multiple dimensions;
adding the data of each dimension in the sub-monitoring data corresponding to each person respectively to obtain a comprehensive score corresponding to each person;
and respectively displaying the comprehensive scores corresponding to the personnel through the line graphs in a second preset area of the two-dimensional plane graph according to the time sequence of the comprehensive scores.
9. The data processing method of claim 8, wherein after the step of displaying the integrated scores corresponding to the respective persons by the line graphs in chronological order of the integrated scores in a second preset area of the two-dimensional plan view, the data processing method further comprises:
displaying a plurality of box whisker graphs in the second preset area based on a third preset time length, wherein the third preset time length is integral multiple of the second preset time length, and the first preset time length is integral multiple of the third preset time length;
when a second display instruction triggered by a target box whisker diagram in a plurality of box whisker diagrams is detected, acquiring the maximum score, the minimum score and the score mean value of the comprehensive scores of all personnel before the moment corresponding to the target box whisker diagram;
and displaying the obtained maximum score, the minimum score and the score mean value.
10. The data processing method of claim 8, wherein after the step of displaying the integrated scores corresponding to the respective persons by the line graphs in chronological order of the integrated scores in a second preset area of the two-dimensional plan view, the data processing method further comprises:
determining whether target normalized data with normalized data of each dimension in corresponding preset ranges exists in the normalized monitoring data corresponding to each person;
if the target normalized data exists, acquiring the acquisition time corresponding to the target normalized data and target personnel;
and displaying a preset graph in a line graph corresponding to the target person based on the acquisition time.
11. A data processing apparatus, characterized in that the data processing apparatus comprises:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for regularly acquiring monitoring data of multiple dimensions corresponding to each person at intervals of a first preset time length;
the second acquisition module is used for respectively carrying out normalization processing on the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data;
the first determining module is used for determining the similarity between every two persons based on the normalized monitoring data of each dimension in each person and determining a similarity matrix corresponding to each person based on the similarity;
and the second determining module is used for determining outlier personnel in the personnel based on the similarity matrix.
12. A data processing apparatus, characterized in that the data processing apparatus comprises: memory, processor and data processing program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the data processing method according to any one of claims 1 to 10.
13. A computer-readable storage medium, characterized in that a data processing program is stored thereon, which when executed by a processor implements the steps of the data processing method according to any one of claims 1 to 10.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010057407.3A CN111243743A (en) | 2020-01-17 | 2020-01-17 | Data processing method, device, equipment and computer readable storage medium |
| PCT/CN2020/129252 WO2021143337A1 (en) | 2020-01-17 | 2020-11-17 | Data processing method, apparatus, and device, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010057407.3A CN111243743A (en) | 2020-01-17 | 2020-01-17 | Data processing method, device, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111243743A true CN111243743A (en) | 2020-06-05 |
Family
ID=70876215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010057407.3A Pending CN111243743A (en) | 2020-01-17 | 2020-01-17 | Data processing method, device, equipment and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111243743A (en) |
| WO (1) | WO2021143337A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021143337A1 (en) * | 2020-01-17 | 2021-07-22 | 深圳前海微众银行股份有限公司 | Data processing method, apparatus, and device, and computer readable storage medium |
| CN114253168A (en) * | 2020-09-22 | 2022-03-29 | 南亚科技股份有限公司 | Machine monitoring system and machine monitoring method |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116933210B (en) * | 2023-09-15 | 2023-11-24 | 山东荷唯美食品有限公司 | Food processing filling equipment monitoring method and system based on multidimensional sensor |
| CN116992391B (en) * | 2023-09-27 | 2023-12-15 | 青岛冠宝林活性炭有限公司 | Hard carbon process environment-friendly monitoring data acquisition and processing method |
| CN117422345B (en) * | 2023-12-18 | 2024-03-12 | 泰安金冠宏食品科技有限公司 | Oil-residue separation quality assessment method and system |
| CN117892248B (en) * | 2024-03-15 | 2024-05-28 | 山东鲁新国合节能环保科技有限公司 | Abnormal data monitoring method in sintering flue gas internal circulation process |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106093703A (en) * | 2016-06-07 | 2016-11-09 | 湖南大学 | The identification of a kind of intelligent distribution network fault and localization method |
| CN106124929A (en) * | 2016-06-30 | 2016-11-16 | 湖南大学 | A kind of power distribution network physical fault and information fault identification method |
| CN107562778A (en) * | 2017-07-21 | 2018-01-09 | 哈尔滨工程大学 | A kind of outlier excavation method based on deviation feature |
| CN109582741A (en) * | 2018-11-15 | 2019-04-05 | 阿里巴巴集团控股有限公司 | Characteristic treating method and apparatus |
| CN110119493A (en) * | 2019-04-09 | 2019-08-13 | 浙江大学 | A kind of Power System Events cognitive method based on compression PMU data and the local factor that peels off |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5533894B2 (en) * | 2011-05-17 | 2014-06-25 | 株式会社豊田中央研究所 | Outlier detection device, outlier detection method, program, and vehicle fault diagnosis system |
| CN104714964B (en) * | 2013-12-13 | 2018-03-23 | 中国移动通信集团公司 | A kind of physiological data Outliers Detection method and device |
| CN111242695A (en) * | 2020-01-17 | 2020-06-05 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN111243743A (en) * | 2020-01-17 | 2020-06-05 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and computer readable storage medium |
-
2020
- 2020-01-17 CN CN202010057407.3A patent/CN111243743A/en active Pending
- 2020-11-17 WO PCT/CN2020/129252 patent/WO2021143337A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106093703A (en) * | 2016-06-07 | 2016-11-09 | 湖南大学 | The identification of a kind of intelligent distribution network fault and localization method |
| CN106124929A (en) * | 2016-06-30 | 2016-11-16 | 湖南大学 | A kind of power distribution network physical fault and information fault identification method |
| CN107562778A (en) * | 2017-07-21 | 2018-01-09 | 哈尔滨工程大学 | A kind of outlier excavation method based on deviation feature |
| CN109582741A (en) * | 2018-11-15 | 2019-04-05 | 阿里巴巴集团控股有限公司 | Characteristic treating method and apparatus |
| CN110119493A (en) * | 2019-04-09 | 2019-08-13 | 浙江大学 | A kind of Power System Events cognitive method based on compression PMU data and the local factor that peels off |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021143337A1 (en) * | 2020-01-17 | 2021-07-22 | 深圳前海微众银行股份有限公司 | Data processing method, apparatus, and device, and computer readable storage medium |
| CN114253168A (en) * | 2020-09-22 | 2022-03-29 | 南亚科技股份有限公司 | Machine monitoring system and machine monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021143337A1 (en) | 2021-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111243743A (en) | Data processing method, device, equipment and computer readable storage medium | |
| US11275932B2 (en) | Human body attribute recognition method, apparatus, and device and medium | |
| US10956753B2 (en) | Image processing system and image processing method | |
| US9833196B2 (en) | Apparatus, system, and method for detecting activities and anomalies in time series data | |
| US9710761B2 (en) | Method and apparatus for detection and prediction of events based on changes in behavior | |
| US20150100355A1 (en) | Method and apparatus for identifying early status | |
| CN111126153B (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
| CN110503082B (en) | Model training method based on deep learning and related device | |
| CN110751809A (en) | Construction safety monitoring method and related product | |
| WO2021036634A1 (en) | Fault detection method and related product | |
| CN103106394A (en) | Human body action recognition method in video surveillance | |
| CN113139403A (en) | Violation behavior identification method and device, computer equipment and storage medium | |
| CN114469076A (en) | Identity feature fused old solitary people falling identification method and system | |
| JP7075460B2 (en) | Information recognition system and its method | |
| CN110717461A (en) | Fatigue state identification method, device and equipment | |
| Mohan et al. | Non-invasive technique for real-time myocardial infarction detection using faster R-CNN | |
| CN113384267A (en) | Fall real-time detection method, system, terminal equipment and storage medium | |
| CN113435753A (en) | Enterprise risk judgment method, device, equipment and medium in high-risk industry | |
| CN114463779A (en) | Smoking identification method, device, equipment and storage medium | |
| US11317870B1 (en) | System and method for health assessment on smartphones | |
| CN116071784A (en) | Personnel illegal behavior recognition method, device, equipment and storage medium | |
| CN110826490A (en) | Track tracking method and device based on step classification | |
| US11954955B2 (en) | Method and system for collecting and monitoring vehicle status information | |
| CN114373142A (en) | Pedestrian falling detection method based on deep learning | |
| US11749021B2 (en) | Retrieval device, control method, and non-transitory storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |